An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

Awesome List for Agentic RL

[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)

Official repository for "RLVR-World: Training World Models with Reinforcement Learning" (NeurIPS 2025), https://arxiv.org/abs/2505.13934

[ICLR 2026] An official implementation of "CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning"

🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models

Implementation of GradLoc from the Tencent Hunyuan blog "Stabilizing RLVR via Token-level Gradient Diagnosis and Layerwise Clipping".

Codes for the paper "BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping" by Zhiheng Xi et al.

A curated list of awesome resources about reward construction for AI agents. This repository covers cutting-edge research, and practical guides on defining and collecting rewards to build more intelligent and aligned AI agents.

a Python library that uses Reinforcement Learning (RL) to train LLMs.

Procedural data generators suite for synthetic pretraining and formal reasoning

Enemies for your LLM

🐝 SwarmBench: Benchmarking LLMs' Swarm Intelligence

This is the official code of DeepSearch [ICLR 2026]

The official repository of the paper "Do Reasoning Models Enhance Embedding Models?"

Tinker ↔ KernelBench Integration enabling RL for GPU Kernel Generation

CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR

grpo to train long form QA and instructions with long-form reward model

MOTIF: Modular Thinking via Reinforcement Fine-tuning in LLMs

PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory